SLICC Browser-Native Agent
Operate browsers, shells, files, and authenticated apps from one agent workspace.
- Source repo
- ai-ecoverse/slicc
- Stars
- ★ 37
- Last updated
- today
- License
- Apache-2.0
- Primary language
- TypeScript
- FA score
- 64/100 · Some gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformClaude API
- Cost
- Free software; you pay for model usage
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A developer who works across browsers and terminals can edit files, run tools, and verify application behavior without leaving one workspace.
- Not a fit if
- Users who need a native Windows or Linux GUI
- Teams that cannot tolerate an active prototype breaking
- Users unwilling to configure model-provider credentials
- Source review
- 64/100 · Some gaps
What does this agent do, and when should you use it?
SLICC, short for Self-Licking Ice Cream Cone, is an agent runtime that lives inside a browser and can control that browser. It combines a virtual filesystem, a practical shell, Playwright-based browser automation, generated interfaces, and multi-agent delegation in one workspace for development and authenticated web tasks. Users can enter through the hosted web app, macOS application, Node.js CLI, Chrome extension, or headless follower CLI; the same core also spans Electron, an iOS follower, GitHub Actions, and cloud execution. A primary agent called a Cone can delegate work to Scoops with isolated sandboxes, shells, and conversation histories, then collect their results. The repository describes the product as an active working prototype: the macOS app is currently the easiest entry point, while native Windows and Linux graphical interfaces are not yet available.
After a user gives a Cone a task, SLICC can read and edit workspace or mounted files, run commands such as bash, git, node, python, grep, and playwright, inspect pages, control tabs, capture screenshots, and act in authenticated browser applications. It can connect additional browser windows into a Tray, attach to Electron applications, and embed a follower in third-party pages through @ai-ecoverse/cherry. A Cone can spawn isolated Scoops to perform subtasks in parallel; their results, durable error cards, file links, images, and generated interfaces return to the chat workspace. mount --source exposes S3, Cloudflare R2, MinIO, da.live, and AEM Source Bus content through the VFS, while serve --bridge and serve --ttl 30d publish live driveable previews or time-limited immutable snapshots. Before conversation compaction, SLICC stores the full transcript under /sessions; the optional Memory v2 gelatiere can review archived sessions and suggest skills or workflows.
- A developer who works across browsers and terminals can edit files, run tools, and verify application behavior without leaving one workspace.
- An operations user can automate repetitive steps in an already authenticated web application using page inspection, screenshots, storage access, and scripted tab control.
- A technical power user can split a large research, implementation, or validation job across isolated Scoops and have the Cone coordinate the findings.
- A user away from the main machine can join the same Tray from another browser, the iPhone or iPad follower, or the Go
sliccCLI. - A CI team can run a leader on a GitHub Actions runner, mount a repository, submit a prompt, and retrieve the generated file within a workflow.
- A content or engineering team can expose local folders and supported S3-compatible or Adobe content stores through a common virtual filesystem.
How do you install or deploy this agent?
The fastest local path requires Node.js 22 or later and Google Chrome: run npx sliccy, then configure an LLM provider in the first-run settings dialog. For a global installation, run npm install -g sliccy followed by slicc. To develop from source, run git clone https://github.com/ai-ecoverse/slicc.git, cd slicc, npm install, and npm run dev; this starts the Node server with Vite HMR and opens http://localhost:5710. macOS users can alternatively download the latest .dmg from the repository releases. Install the headless follower with npx sliccy --install-cli; native Windows also supports irm https://www.sliccy.ai/install-cli.ps1 | iex.
How do you use this agent?
Start with npx sliccy, choose and configure a supported model provider during first-run setup, and describe a task in the workspace composer. The agent can then use its shell, VFS, and the current browser session. To expose a host folder, mount it at an empty path, for example npx slicc --mount=~/Projects/foo:/mnt/foo; remove it with umount /mnt/foo. To add another browser, choose “Enable multi-browser sync” from the avatar menu, copy the sync URL, and use “Connect to another browser” in the second browser. For Electron, use a command such as npm run dev:electron -- /Applications/Slack.app. After configuring server-side credentials, a remote store can be mounted with a command such as mount --source s3://my-bucket --profile r2 /mnt/r2.
What are this agent's strengths and limitations?
- The agent loop, VFS, shell, UI, and tools run primarily in the browser and can act on the same browser hosting the workspace.
- One core supports hosted web, CLI, Chrome extension, Electron, macOS and iOS followers, GitHub Actions, and cloud-oriented execution paths.
- The Cone/Scoop model provides parallel delegation with separate sandboxes and contexts instead of forcing every task into one conversation.
- Its working environment includes practical command-line tools plus local and remote mounts for S3, R2, MinIO, da.live, and AEM sources.
- Domain-scoped secret injection keeps real credential values hidden from the agent.
- The project is explicitly an active prototype, and its intended audience is expected to tolerate occasional breakage.
- The local CLI requires Node.js 22 or later and Chrome; no native Windows or Linux graphical interface is currently available.
- Users must supply and configure model-provider credentials or allowances, and several listed providers are described as unverified YMMV options.
- The Chrome extension is a thin CDP bridge that loads the hosted leader application rather than a self-contained bundled agent UI.
serve --bridgecarries a documented cross-subdomain cookie risk: cookies set forDomain=.sliccy.noware readable across previews.
How does this agent compare with similar options?
The repository positions SLICC in the OpenClaw-alternative space and credits OpenClaw, NanoClaw, and Pi as inspirations; Pi is described as the core inside every SLICC instance. SLICC's stated distinction is that the agent runtime lives in and controls the browser, while combining a shell, VFS, multi-browser Trays, Electron attachment, and delegated Scoops in the same workspace.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| SLICC Browser-Native Agent This agent | 64 · Some gaps | CLIFree + model costs | ★ 37 | today | TypeScript | Claude API |
| Rakazo AI Teammates | 80 · Good | Self-hosted serviceFree + model costs | ★ 7.5k | today | TypeScript | — |
| Octop Self-Hosted Assistant | 58 · Major gaps | CLIFree + model costs | ★ 12k | 1d ago | Python | Codex · Claude Code · OpenAI API |
| AI Research Skills | 72 · Some gaps | Agent plugin / skillFree + model costs | ★ 617 | 1d ago | Python | Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
The documentation describes granular sudo rules, genuine user or OS approval for sensitive actions, server-side retention of mount credentials, and cross-subdomain cookie risk for previews. These support the confirmation, data-flow, and sensitive-data scores. Deductions reflect broad capabilities including local filesystem mounts, shell, browser control, and remote control of tray apps; the default sudo template gates only the model configuration file; and the packet does not show a complete tool permission inventory, dependency audit, or revocation path for all external actions.
README and the architecture hub are broadly consistent about browser, CLI, extension, and tray runtimes, and describe persistent failures, retry bounds, rereads after concurrent edits, and preview revocation. Deductions reflect the lack of dependency locking/availability evidence or runtime evidence in this packet; the README is very long and some limitations appear only within feature-specific sections.
README names concrete scenarios including development, browser automation, authenticated app workflows, research, and cross-runtime use, and states that macOS is the primary desktop UI while other desktop UIs are unavailable and the project is a working prototype. Deductions reflect that runtime-specific capabilities and permissions must be assembled from scattered sections; the RFC 8288 Link handoff approval flow is also not immediately clear to ordinary readers.
The repository hub organizes modules, runtimes, and documentation tiers; README provides several installation paths, many examples, and some limitations; an Apache-2.0 LICENSE is present. Deductions reflect no clear version or change summary, no stated maintenance owner or update commitment in the packet, and varied product spellings such as SLICC, Slicc, and sliccy.
The product combines browser control, shell, files, skills, and parallel agents into an actionable workspace with broad use cases and output forms. Deductions reflect no overall cost or resource guidance and a substantial learning burden from advanced features, configuration, and security boundaries; static materials cannot establish actual result quality.
Descriptions of major capabilities and safeguards recur across README, approvals and OAuth documentation, and SDK interface comments; some behaviors have concrete paths, parameters, and limits. Deductions reflect that many claims remain documentary assertions, while this sample lacks enough implementation code or complete test contents for item-by-item confirmation; it also does not systematically distinguish observed facts from inference.
- The product can use a shell, mount local directories, control browsers, and connect other browsers or Electron apps; review mount scope and approval policy before use.
- Some preview functionality explicitly accepts the risk that Domain=.sliccy.now cookies can be read across previews; avoid exposing sensitive session data there.
- The repository describes an active working prototype, with the macOS app as the easiest desktop entry point; this packet does not establish runtime outcomes or dependency security.
Maintain this project? Add the FARS badge to your README
[](https://followagents.com/en/agents/slicc)<a href="https://followagents.com/en/agents/slicc"><img src="https://followagents.com/badge/slicc.svg" alt="FARS review"></a>Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
[6.258.5](https://github.com/ai-ecoverse/slicc/compare/v6.258.4...v6.258.5) (2026-11-08) Bug Fixes * deps: update dependency isomorphic-git to v1.44.9 ([9ee1ec9](https://github.com/ai-ecoverse/slicc/commit/9ee1ec98d8745ff7d6667c09d9a461b3f36c79e4)) * webapp: keep ZenFS ctime stable under isomorphic-git 1.44.9 ([b00cf25](https://github.com/ai-ecoverse/slicc/commit/b00cf2590173856ea2635b88ffa9a7ca8ae10555))View on GitHub ↗ -
Release notes excerpt
[6.258.4](https://github.com/ai-ecoverse/slicc/compare/v6.258.3...v6.258.4) (2026-11-08) Bug Fixes * webapp: strip temperature from quick-llm calls that reject it ([5e701b2](https://github.com/ai-ecoverse/slicc/commit/5e701b2932bff3d950d6224637d63e64f10f5691)), closes [#4239](https://github.com/ai-ecoverse/slicc/issues/4239)View on GitHub ↗ -
Release notes excerpt
[6.258.3](https://github.com/ai-ecoverse/slicc/compare/v6.258.2...v6.258.3) (2026-11-07) Bug Fixes * deps: update dependency lucide to v1.66.0 ([47a8f1c](https://github.com/ai-ecoverse/slicc/commit/47a8f1c7867ebcc97e3df9c8118a97fbba057c45))View on GitHub ↗
FAQ
Does SLICC require a paid account?
What local access does it receive?
Can it run on Windows or Linux?
What happens when a provider fails or runs out of quota?
Can the agent read stored credentials?
~/.slicc/secrets.env for the CLI or chrome.storage.local for the extension.Thanks — we use this to improve the page.